斗图图片爬取

# -*- coding:utf8 -*-import requestsimport timefrom lxml import etreeclass DouTu:    def __init__(self):        self.header = {            "User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64; rv:47.0) Gecko/20100101 Firefox/47.0"        }    #设置header头    def get_url(self,page):        url = "https://www.doutula.com/photo/list/"+page        #设置页面链接        response = requests.get(url=url,headers=self.header).text        #获取页面信息        self.parse_url(response)    def parse_url(self,response):        html = etree.HTML(response)        link = html.xpath('//div[@class="page-content text-center"]/div/a/@href')        #获取详情页面的链接        # print(link)        for i in link:            # print(i)            self.parse(i)            #将链接进行循环            time.sleep(3)            #设置延迟时间    def parse(self,i):        response = requests.get(url=i,headers=self.header).text        #详情页面的纤细        html = etree.HTML(response)        name = html.xpath('//div[@class="pic-title"]/h1/a/text()')[0]        #图片的名字        img = html.xpath(".//*[@id='detail']/div/div[1]/li/div[3]/div/div/div/div[1]/table/tbody/tr[1]/td/img/@src")[0]        #图片的链接        # print(img)        self.write(name,img)    def write(self,name,img):        #将推按写入文件        try:#进行异常处理            response = requests.get(url=img,headers=self.header).content            #过去图片的链接信息            with open('图片/%s' % name +'.jpg', 'wb') as f:            #with open 打开一个文件夹加上图片名字进行存储                f.write(response)                print('成功')        except:            print('图片有问题,跳过!')if __name__ == '__main__':    dt = DouTu()    for i in range(1,51):#设置分页爬取        print("第%s页开始"%i)        page = '?page=%s'%i        dt.get_url(page)        print("第%s页结束"%i)